Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3609 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0962. Min Range: -1.0962

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1882786 (The Pile)

Max Activating Token Index: 423

Text #1

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.5883. Min Act: -0.0000

Data Index: 85138 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1186777 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.5462. Min Act: -0.0000

Data Index: 232647 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1560425 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4997. Min Act: -0.0000

Data Index: 895033 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4709. Min Act: -0.0000

Data Index: 859525 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1138692 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1498754 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4430. Min Act: -0.0000

Data Index: 95920 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1169133 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4627. Min Act: -0.0000

Data Index: 772345 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1500301 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.3668. Min Act: -0.0000

Data Index: 852673 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4227. Min Act: -0.0000

Data Index: 439578 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1125424 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.4030. Min Act: -0.0000

Data Index: 937610 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.3829. Min Act: -0.0000

Data Index: 251780 (The Pile)

Max Activating Token Index: 277

Text #18

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.3837. Min Act: -0.0000

Data Index: 3553 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1739496 (The Pile)

Max Activating Token Index: 560